Analysis Plots

<<<<<<< HEAD

ny_local = 
  read_csv("./data/ny_local.csv")

## Parsed with column specification:
## cols(
##   .default = col_character(),
##   year = col_double(),
##   data_value = col_double(),
##   low_confidence_limit = col_double(),
##   high_confidence_limit = col_double(),
##   population_count = col_double(),
##   city_fips = col_double(),
##   tract_fips = col_double()
=======
library(tidyverse)
## ── Attaching packages ─────────────────────────────────────────────────────────────────────── tidyverse 1.3.0 ──
## ✓ ggplot2 3.3.2     ✓ purrr   0.3.4
## ✓ tibble  3.0.3     ✓ dplyr   1.0.2
## ✓ tidyr   1.1.2     ✓ stringr 1.4.0
## ✓ readr   1.3.1     ✓ forcats 0.5.0
## ── Conflicts ────────────────────────────────────────────────────────────────────────── tidyverse_conflicts() ──
## x dplyr::filter() masks stats::filter()
## x dplyr::lag()    masks stats::lag()
library(flexdashboard)
library(plotly)
## 
## Attaching package: 'plotly'
## The following object is masked from 'package:ggplot2':
## 
##     last_plot
## The following object is masked from 'package:stats':
## 
##     filter
## The following object is masked from 'package:graphics':
## 
##     layout
ny_local = 
  read_csv("./data/500_Cities.csv") %>% 
  janitor::clean_names() %>% 
  filter(state_abbr == "NY")
## Parsed with column specification:
## cols(
##   .default = col_character(),
##   Year = col_double(),
##   Data_Value = col_double(),
##   Low_Confidence_Limit = col_double(),
##   High_Confidence_Limit = col_double(),
##   PopulationCount = col_double()
>>>>>>> c39ca86df3e1516e8c6788dba9336907f1464f4d
## )
## See spec(...) for full column specifications.
covid_symptom_df =
  read_csv("./data/Anxiety_Depression.csv") %>% 
  janitor::clean_names() %>% 
  filter(state == "New York") %>% 
  mutate(
    indicator_id = case_when(
      indicator == "Symptoms of Anxiety Disorder" ~ "Anxiety",
      indicator == "Symptoms of Anxiety Disorder or Depressive Disorder" ~ "Anxiety/Depressive",
      indicator == "Symptoms of Depressive Disorder" ~ "Depressive"
  ))
## Parsed with column specification:
## cols(
##   Phase = col_double(),
##   Indicator = col_character(),
##   Group = col_character(),
##   State = col_character(),
##   Subgroup = col_character(),
##   `Time Period` = col_double(),
##   `Time Period Label` = col_character(),
##   Value = col_double(),
##   `Low CI` = col_double(),
##   `High CI` = col_double(),
##   `Confidence Interval` = col_character(),
##   `Quartile range` = col_character()
## )
mental_care_df =
  read_csv("./data/Mental_Health_Care.csv") %>% 
  janitor::clean_names() %>% 
  filter(state == "New York") %>% 
  mutate(
    indicator_id = case_when(
      indicator == "Needed Counseling or Therapy But Did Not Get It, Last 4 Weeks" ~ "No Therapy",
      indicator == "Received Counseling or Therapy, Last 4 Weeks" ~ "Therapy",
      indicator == "Took Prescription Medication for Mental Health And/Or Received Counseling or Therapy, Last 4 Weeks" ~ "Med/Therapy",
      indicator == "Took Prescription Medication for Mental Health, Last 4 Weeks" ~ "Med"
    )
  )
## Parsed with column specification:
## cols(
##   Indicator = col_character(),
##   Group = col_character(),
##   State = col_character(),
##   Subgroup = col_character(),
##   Phase = col_double(),
##   `Time Period` = col_double(),
##   `Time Period Label` = col_character(),
##   Value = col_double(),
##   LowCI = col_double(),
##   HighCI = col_double(),
##   `Confidence Interval` = col_character(),
##   `Quartile Range` = col_character(),
##   `Suppression Flag` = col_double()
## )
<<<<<<< HEAD
=======
chronic_df = 
  read_csv("./data/Chronic_Disease_Indicators.csv") %>% 
  janitor::clean_names()
## Parsed with column specification:
## cols(
##   .default = col_character(),
##   YearStart = col_double(),
##   YearEnd = col_double(),
##   Response = col_logical(),
##   DataValue = col_double(),
##   DataValueAlt = col_double(),
##   LowConfidenceLimit = col_double(),
##   HighConfidenceLimit = col_double(),
##   StratificationCategory2 = col_logical(),
##   Stratification2 = col_logical(),
##   StratificationCategory3 = col_logical(),
##   Stratification3 = col_logical(),
##   ResponseID = col_logical(),
##   StratificationCategoryID2 = col_logical(),
##   StratificationID2 = col_logical(),
##   StratificationCategoryID3 = col_logical(),
##   StratificationID3 = col_logical()
## )
## See spec(...) for full column specifications.
>>>>>>> c39ca86df3e1516e8c6788dba9336907f1464f4d
write_csv(ny_local, "./data/ny_local.csv")

Page 1

Column

Chart 1
ub_overall_plot =
  ny_local %>% 
  select(category, measure_id, data_value) %>% 
  filter(category == "Unhealthy Behaviors") %>% 
  ggplot(aes(x = measure_id, y = data_value, color = measure_id)) +
  geom_boxplot() +
  labs(
    x = "Unhealthy Behavior",
    y = "Prevalence (%)"
  ) +
  scale_y_continuous(limits = c(0, 100))

ggplotly(ub_overall_plot)
## Warning: Removed 140 rows containing non-finite values (stat_boxplot).
<<<<<<< HEAD


=======


>>>>>>> c39ca86df3e1516e8c6788dba9336907f1464f4d



Column

Chart 2
mental_health_value =
  ny_local %>%
  select(unique_id, data_value, measure_id, population_count) %>% 
  filter(measure_id == "MHLTH") %>% 
  mutate(value_mental = data_value) %>% 
  select(unique_id, value_mental, population_count)

current_smoking_value =
  ny_local %>%
  select(unique_id, data_value, measure_id, population_count) %>% 
  filter(measure_id == "CSMOKING") %>% 
  mutate(value_smoking = data_value) %>% 
  select(unique_id, value_smoking, population_count)

mental_smoking =
<<<<<<< HEAD
  left_join(mental_health_value, current_smoking_value) %>% 
  drop_na()
=======
  left_join(mental_health_value, current_smoking_value)

>>>>>>> c39ca86df3e1516e8c6788dba9336907f1464f4d

## Joining, by = c("unique_id", "population_count")

current_smoking_plot =
  mental_smoking %>% 
  ggplot(aes(x = value_mental, y = value_smoking, size = population_count)) +
  geom_point(alpha = 0.5, color = "steel blue") +
  labs(
    x = "Mental Health Prevalence (%)",
    y = "Unhealthy Behavior Prevalence (%)",
    title = "Current Smoking"
  ) +
  scale_y_continuous(limits = c(0, 100)) 

ggplotly(current_smoking_plot)

<<<<<<< HEAD

r_smoking = cor(mental_smoking$value_mental, mental_smoking$value_smoking, method = c("pearson"))
r_smoking

## [1] 0.9487768

=======

>>>>>>> c39ca86df3e1516e8c6788dba9336907f1464f4d